vietnamese ner This model is a fine tuned version of NlpHUST/electra base vn on an VLSP 2018 dataset. It achieves the following results on the evaluation set: Loss: 0.0580 Location Precision: 0.9353 Location Recall: 0.9377 Location F1: 0.9365 Location Number: 2360 Miscellaneous Precision: 0.5660 Miscellaneous Recall: 0.6897 Miscellaneous F1: 0.6218 Miscellaneous Number: 174 Organization Precision: 0.8610 Organization Recall: 0.9068 Organization F1: 0.8833 Organization Number: 1878 Person Precision: 0.9692 Person Recall: 0.9637 Person F1: 0.9664 Person Number: 2121 Overall Precision: 0.9122 Overall Recall: 0.9307 Overall F1: 0.9214 Overall Accuracy: 0.9907 Model description More information needed How to use You can use this model with Transformers pipeline for NER. Intended uses & limitations More information needed Training and evaluation data More information needed Training procedure Training hyperparameters The following hyperparameters were used during training: learning rate: 5e 05 train batch size: 16 eval batch size: 4 seed: 42 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e 08 lr scheduler type: linear num epochs: 10.0 Framework versions Transformers 4.20.1 Pytorch 1…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy